# Iterative Learning for Instance Segmentation

arXiv: https://arxiv.org/abs/2202.09110 · HTML: https://mlsanity.com/paper/2202.09110/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 18 Feb 2022.

## Builds on (most cited first, 10 of 10)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [A Survey of Human-in-the-loop for Machine Learning](https://mlsanity.com/paper/2108.00941/) (2021)
- [Extended Feature Pyramid Network for Small Object Detection](https://mlsanity.com/paper/2003.07021/) (2020)
- [Iterative Bounding Box Annotation for Object Detection](https://mlsanity.com/paper/2007.00961/) (2020)
- [Semi-Automatic Annotation For Visual Object Tracking](https://mlsanity.com/paper/2101.06977/) (2021)
- [Sample selection for efficient image annotation](https://mlsanity.com/paper/2105.04678/) (2021)

## Abstract (arXiv)

Instance segmentation is a computer vision task where separate objects in an image are detected and segmented. State-of-the-art deep neural network models require large amounts of labeled data in order to perform well in this task. Making these annotations is time-consuming. We propose for the first time, an iterative learning and annotation method that is able to detect, segment and annotate instances in datasets composed of multiple similar objects. The approach requires minimal human intervention and needs only a bootstrapping set containing very few annotations. Experiments on two different datasets show the validity of the approach in different applications related to visual inspection.